agentleFS
bloxy-studiosbloxy-studios/shorts-studio/skills/revise/SKILL.md

revise

Skill0 starsChanged 42 days agoMITView on GitHub

Apply natural-language changes to an existing short as typed operations on a new EditPlan version — trims/extensions, keep both speakers visible, speaker switches, calmer motion, caption style/emphasis/zone/word corrections, music level, voice cleanup — with targeted cache invalidation, a readable diff, and re-render + QA.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use submit.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • H-mmerSkill

    submit

    Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.

    Also in 3 projects that use this

The file

Files
SKILL.md

Revise an edit

Rules: ${CLAUDE_PLUGIN_ROOT}/references/rules.md · CLI (all ops): ${CLAUDE_PLUGIN_ROOT}/references/cli.md. ss = "${CLAUDE_PLUGIN_ROOT}/bin/shorts-studio". Input: $ARGUMENTS

0. Engine check

The commands below run the Shorts Studio engine. Installed as the Claude Code plugin it is already present and shorts-studio is on the Bash PATH. If shorts-studio doctor is not found (for example, this skill was added with npx skills add), ask the user before installing anything, then:

  • Claude Code: /plugin marketplace add bloxy-studios/shorts-studio → /plugin install shorts-studio@shorts-studio.
  • Other agents: git clone --depth 1 https://github.com/bloxy-studios/shorts-studio ~/.shorts-studio/engine and read every ${CLAUDE_PLUGIN_ROOT} path below as ~/.shorts-studio/engine.

Then run shorts-studio doctor --setup once (project-local runtime; never sudo or global installs).

Steps

  1. Map the request to ops (state the timebase: output time unless the user quotes source time):
    RequestOp
    end later/earlier, start earlier/laterextend-end / trim-end / extend-start / trim-start (ms)
    keep both people visiblekeep-both-visible (from, to)
    switch to the other speaker hereswitch-speaker (at)
    less motion / calmerreduce-motion
    cleaner / different caption lookcaption-style (styleId) — preview first if unsure (preview skill)
    highlight these words / fewer highlightscaption-emphasis (keywords, onlyKeywords, mode)
    wrong word in captionscaption-correct (from, to, at) — timing unchanged, correction recorded
    move captionscaption-zone (from, to, y0, y1, reason)
    music quieter/loudermusic-gain (db) — voice untouched
    voice cleanupvoice-chain (denoise, deess, compress, highpassHz)
    Luxury graphics changes are brief edits instead: update luxury/graphics.json, then ss luxury plan.
  2. ss revise <project> --clip <id> --reason "<user's words>" --op '{…}' [--op …] → new plan version, diff, invalidated stages (unchanged stages reuse caches).
  3. ss render <project> --clip <id> → QA. Inspect the changed region on real frames (qa/cuts.jpg, or extract frames).
  4. The approved render is never overwritten (approve marks finals).

Errors and limits

  • Extending past the source, trimming the whole segment, or a word not in the captions → the op fails with the reason; ask/adjust.
  • keep-both-visible needs two faces in the range (else say so and offer a stack/wide layout).

Example

"Keep both of them visible from 1.3 to 4.3 and make the music 2 dB quieter" → ss revise p --clip clip-01 --reason "…" --op '{"op":"keep-both-visible","from":"0:01.3","to":"0:04.3"}' --op '{"op":"music-gain","db":-2}' → ss render p --clip clip-01.

Completion check

A new plan version exists with the user's reason in its changes; the re-render's QA has no new hard failure; you looked at frames in the changed range and reported what changed (and what did not).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.